░▒▓███████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░
░▒▓█▓▒░ ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓█▓▒░ ░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓██████▓▒░░▒▓███████▓▒░░▒▓████████▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓███████▓▒░
░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░
░▒▓███████▓▒░░▒▓█▓▒░░▒▓█▓▒░▒▓█▓▒░░▒▓█▓▒░░▒▓██████▓▒░░▒▓███████▓▒░
发现 AI Agent Skills
为你的 AI 智能体查找、分享并部署可复用技能
npm i -g skhub
Footprint integration. Manage data, records, and automate workflows. Use when the user wants to interact with Footprint data.
00
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).
00
Use this skill when the user needs to run Google Ads, write ad copy, select keywords, optimize CAC/LTV, or manage a small paid acquisition budget. Covers Google Ads strategy, keyword selection, ad copywriting, and conversion tracking for bootstrapped SaaS.
00
Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences. Like NY Times interactives, Apple product pages, and award-winning web experiences.
00
Configure Cloudflare DDoS protection with managed rulesets, rate limiting, WAF rules, Bot Management, and origin protection to mitigate volumetric, protocol, and application-layer attacks.
00
MCP server for accessing Monarch Money personal finance data through Claude Desktop and Claude Code
00
Agent skill for user-tools - invoke with $agent-user-tools
00
Build Godot 4.7 user interfaces with Control nodes: anchors and offsets for responsive layout, Container nodes (VBox/HBox/Grid/Margin) for automatic arrangement, Theme resources for consistent styling, and keyboard/gamepad focus navigation. Use when laying out a HUD, menu, or UI in a Godot project, working with Control/Container nodes, anchors, themes, or focus in a .tscn.
00
Automate Segment tasks via Rube MCP (Composio): track events, identify users, manage groups, page views, aliases, batch operations. Always search tools first for current schemas.
00
Curated bundle for building, testing, and coordinating AI agent systems. Includes multi-agent orchestration, agent testing, cross-agent handoff, MCP server building, and prompt engineering. Use when developing AI agent workflows or multi-agent systems.
00
You are a GitHub issue resolution expert specializing in systematic bug investigation, feature implementation, and collaborative development workflows. Your expertise spans issue triage, root cause an
00
FLOW framework integration for bloggers. Evidence-led content workflow using the Find, Optimize, Win loop with stage-specific AI prompts from the FLOW knowledge base (30 blog-applicable prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "blog flow", "evidence-led blogging", "find optimize win", or wants stage-specific blog prompts.
00
Research Google Trends keyword momentum, regional interest, and related queries. Use search-interest evidence without treating it as sales or total demand.
00
Prompt for creating detailed feature implementation plans, following Epoch monorepo structure.
00
Create ridiculously good content using Ann Handley's "Everybody Writes" methodology—practical, reader-focused writing that serves your audience and achieves your goals. Use when: **Write blog posts** that engage and convert readers; **Create email content** that gets opened and clicked; **Craft social media posts** that stop the scroll; **Develop website copy** that speaks to your audience; **Write thought leadership** that builds credibility
00
Deep code review of a single open PR in nrwl/nx. Checks the PR out only inside an isolated sandbox, then runs four fixed reviewers: implementation (correctness, errors, types, performance), verification (tests, ticket grounding, comments, and docs), approach, and security. A reproduce-verifier executes a runnable repro only when verification identifies one. The skill saves a GitHub-flavored draft to ~/.nx-pr-reviews/<NUMBER>.md and never posts it. Claude reads/executes PR code only through the sandbox CLI; credentials never enter the sandbox.
00
Diagnose the po Pushover plugin and check remaining monthly quota. Runs a full self-test (credential resolution via 1Password/Keychain, /users/validate.json, quota, expected custom sounds present, deps bun/uv/Chrome for Testing with system Chrome as the fallback, audit log) and reports message quota remaining. Use when the user asks if Pushover is working, why a notification failed, how many messages are left, or wants a health/diagnostic check. TRIGGERS - pushover health, po doctor, pushover not working, pushover quota, messages left, diagnose pushover.
00
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legal_hold fields in _log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
00